Created
May 28, 2012 17:06
-
-
Save vadimii/2820112 to your computer and use it in GitHub Desktop.
WSGI Sanitizer
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import webapp2 | |
import html5lib | |
from html5lib import sanitizer,treebuilders,treewalkers | |
from html5lib.serializer.htmlserializer import HTMLSerializer | |
class MainPage(webapp2.RequestHandler): | |
def post(self): | |
self.response.headers['Content-Type'] = 'text/plain' | |
TREE = 'lxml' | |
input_data = self.request.get('content') | |
parser = html5lib.HTMLParser( | |
tree=html5lib.treebuilders.getTreeBuilder(TREE), | |
tokenizer=sanitizer.HTMLSanitizer) | |
output_tree = parser.parse(input_data) | |
walker = treewalkers.getTreeWalker(TREE) | |
output_stream = walker(output_tree) | |
serializer = HTMLSerializer( | |
quote_attr_values=True, | |
omit_optional_tags=True) | |
output_data = serializer.render(output_stream) | |
self.response.out.write(output_data) | |
mappings = [('/', MainPage)] | |
app = webapp2.WSGIApplication(mappings) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment